Training in progress, epoch 0

config.json

@@ -1,9 +1,86 @@
 
 {
-    "_name_or_path": "dekelzak/MERT-v1-95M-finetuned-DEAM_stripped_vocals",
-    "architectures": [
-      "MERTModel"
-    ],
-    "model_type": "mert_model"
-  }
-  
+  "_name_or_path":  "dekelzak/MERT-v1-95M-finetuned-DEAM_stripped_vocals",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "MERTModel"
+  ],
+  "attention_dropout": 0.1,
+  "attention_relax": -1.0,
+  "auto_map": {
+    "AutoConfig": "configuration_MERT.MERTConfig",
+    "AutoModel": "modeling_MERT.MERTModel"
+  },
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "deepnorm": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "feature_extractor_cqt": false,
+  "feature_extractor_cqt_bins": 336,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "mert_model",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "sample_rate": 24000,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a31db468522ac5adafa5c0d0d69040d525fe074c6bbe84eabd31a08d143768
+oid sha256:2b4294ba5c8ed03e1a19fe815bc696f01137c2a2ae9bc9c546fc4b54be4a0811
 size 377518200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca357c901e0a69d2dec97e14621713e86c5a5bad8fc926bd31ed0c83972e5a47
-size 5304
+oid sha256:a5b56e745340ef21e25edbe1af88da54bb8e30e746e9d19ef7fdd05a13b7449e
+size 5368